{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29034959", "kind": "science-record", "revision": 6, "content_hash": "sha256:d03d4baf9651d8587b23e66365ed93c3a5df2899387501a098ea89a190267c31", "created_at": "2026-11-01T15:40:29Z", "updated_at": "2026-11-01T21:21:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Quantitative proteomics of a B12 -dependent alga grown in coculture with bacteria reveals metabolic tradeoffs required for mutualism.", "doi": "10.1111/nph.14832", "pmid": "29034959", "authors": ["Katherine E Helliwell", "Jagroop Pandhal", "Matthew B Cooper", "Joseph Longworth", "Ulrich Johan Kudahl", "David A Russo", "Eleanor V Tomsett", "Freddy Bunbury", "Deborah L Salmon", "Nicholas Smirnoff", "Phillip C Wright", "Alison G Smith"], "journal": "The New phytologist", "year": 2018, "abstract": "The unicellular green alga Lobomonas rostrata requires an external supply of vitamin B12 (cobalamin) for growth, which it can obtain in stable laboratory cultures from the soil bacterium Mesorhizobium loti in exchange for photosynthate. We investigated changes in protein expression in the alga that allow it to engage in this mutualism. We used quantitative isobaric tagging (iTRAQ) proteomics to determine the L. rostrata proteome grown axenically with B12 supplementation or in coculture with M. loti. Data are available via ProteomeXchange (PXD005046). Using the related Chlamydomonas reinhardtii as a reference genome, 588 algal proteins could be identified. Enzymes of amino acid biosynthesis were higher in coculture than in axenic culture, and this was reflected in increased amounts of total cellular protein and several free amino acids. A number of heat shock proteins were also elevated. Conversely, photosynthetic proteins and those of chloroplast protein synthesis were significantly lower in L. rostrata cells in coculture. These observations were confirmed by measurement of electron transfer rates in cells grown under the two conditions. The results indicate that, despite the stability of the mutualism, L. rostrata experiences stress in coculture with M. loti, and must adjust its metabolism accordingly.", "claims": [{"id": "claim-method", "statement": "To avoid using arbitrary thresholds for highlighting differentially expressed proteins, a t‐test was performed between replicate conditions to determine significance with fold change.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29034959", "locator": "sections[6] \"Protein identification and quantification\" paragraph 2", "quote": "To avoid using arbitrary thresholds for highlighting differentially expressed proteins, a t‐test was performed between replicate conditions to determine significance with fold change."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange (PXD005046).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29034959", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Data are available via ProteomeXchange (PXD005046)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:29034959"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PXD005046"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PXD005046"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29034959", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/nph.14832", "sha256": "sha256:63546560ab24aaf2c5eed438a8933076f0f6b496bfd18797dd409d4c7264ec04", "bytes": 63939, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/nph.14832", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5765456", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005046", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PXD005046", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005046", "version": null, "note": "Data are available via ProteomeXchange (PXD005046).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (PXD005046).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Reduction in photosynthetic capacity in a mutualistic algal-bacterial co-culture revealed by quantitative proteomics", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29034959:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f81a8eb0489ff2044d94a74869507525b08fe622e33d56e14678da922c4cc8d9", "bytes": 11065, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#nph14832-tbl-0001", "version": null, "note": "List of identified proteins altered in abundance in cocultures of Lobomonas rostrata vs axenic cultures", "structure": {"pmcid": "PMC5765456", "section_index": 12, "section_title": "Comparative proteomics reveals fundamental changes in metabolism of L. rostrata when grown in coculture with M. loti", "row_count": 155, "column_count": 5}, "table": {"label": "Table 1", "caption": "List of identified proteins altered in abundance in cocultures of Lobomonas rostrata vs axenic cultures", "rows": [["General function", "Uniprot entry", "Protein ID", "Protein function", "Fold‐change"], ["Protein metabolism", "A8ISZ1", "EF‐3", "Elongation factor EF‐3", "2.69"], ["A8HX38", "eEF1a1", "Eukaryotic translation elongation factor 1 alpha 1 (EC 3.6.5.3)", "2.55"], ["A8J597", "RPL12", "Ribosomal protein L12", "2.42"], ["I2FKQ9", "CPN60C", "Mitochondrial chaperonin 60", "2.41"], ["A8J8M9", "RPS20", "Ribosomal protein S20", "2.18"], ["A8J7C8", "KtRS", "Lysine–tRNA ligase (EC 6.1.1.6) (Lysyl‐tRNA synthetase)", "2.00"], ["Q66YD0", "VIPP1", "Chloroplast vesicle‐inducing protein in plastids 1", "1.98"], ["A8J5Z0", "RPP0", "Acidic ribosomal protein P0", "1.93"], ["A8I403", "RPS19", "Ribosomal protein S19", "1.89"], ["A8HTK7", "TBA1", "PsbA translation factor", "1.72"], ["A8JIB7", "CPN60A", "Chaperonin 60A", "1.72"], ["P25840", "HSP70", "Heat shock 70 kDa protein", "1.70"], ["A8ITH8", "CPN60B2", "Chaperonin 60B2", "1.52"], ["A8JHX9", "EFG2", "Elongation factor 2 (EC 3.6.5.3)", "1.51"], ["A8JCX9", "RPL40", "Ribosomal protein L40", "1.44"], ["A8J9Q1", "IPA1", "Importin subunit alpha", "1.33"], ["A8I232", "EIF2G", "Eukaryotic initiation factor", "1.28"], ["A8JIE0", "CPN20", "Chaperonin 20", "1.17"], ["A8IV59", "TIIC22", "22 kDa translocon at the inner membrane of chloroplasts (Fragment)", "−1.14"], ["A8J7T7", "CEP1", "Cysteine endopeptidase", "−1.16"], ["Q70DX8", "S1PRPS1", "Plastid ribosomal protein S1 (Ribosomal protein S1 homologue)", "−1.27"], ["P17746", "TUFA", "Elongation factor Tu, chloroplastic (EF‐Tu)", "−1.30"], ["E3SC57", "RPL3", "60S ribosomal protein L3 (Fragment)", "−1.34"], ["Q5QEB2", "EFTs", "Elongation factor Ts", "−1.34"], ["A8HME4", "RPS2", "Ribosomal protein S2", "−1.37"], ["A8IA39", "EFG1", "Chloroplast elongation factor G (EC 3.6.5.3)", "−1.41"], ["A8J282", "CYN20", "Peptidyl‐prolyl cis‐trans isomerase (EC 5.2.1.8) plastid", "−1.41"], ["E3SC50", "RPS9", "40S ribosomal protein S9 (Fragment)", "−1.42"], ["Q6Y683", "RAP41", "41 kDa ribosome‐associated protein (chloroplast)", "−1.49"], ["Q6Y682", "RAP38", "38 kDa ribosome‐associated protein (Chloroplast stem‐loop‐binding protein)", "−1.52"], ["Q8HTL1", "RPL5", "50S ribosomal protein L5, chloroplastic", "−1.52"], ["A8IVK1", "RPL8", "Ribosomal protein L8", "−1.53"], ["Q84U21", "ERY2", "50S ribosomal protein L22, chloroplastic", "−1.60"], ["Q7Y258", "PRPS5", "Ribosomal protein S5 (plastid)", "−1.61"], ["Q8GV23", "NAB1", "Nucleic acid binding protein (Putative nucleic acid binding protein)", "−1.90"], ["A8I8Z4", "PRPL1", "Plastid ribosomal protein L1", "−1.91"], ["A8IRU6", "CYN38", "Peptidyl‐prolyl cis‐trans isomerase, cyclophilin‐type (plastid)", "−1.97"], ["O20032", "RPS18", "30S ribosomal protein S18, chloroplastic", "−1.98"], ["A8HWS8", "PRPL28", "Plastid ribosomal protein L28", "−2.75"], ["Photosynthetic electron transfer", "A8IV40", "Fd", "Apoferredoxin", "−1.18"], ["A8I9I9", "Re", "Rieske ferredoxin", "−1.19"], ["A8J0E4", "PSBO", "Oxygen‐evolving enhancer protein 1 of photosystem II", "−1.21"], ["A8HXL8", "ATPC", "Chloroplast ATP synthase gamma chain", "−1.25"], ["B7U1J0", "ATPA", "ATP synthase subunit alpha, chloroplastic (EC 3.6.3.14)", "−1.32"], ["Q6PSL4", "HYDG", "Fe‐hydrogenase assembly protein (Hydrogenase assembly factor)", "−1.36"], ["A8J6Y8", "FNR2", "Ferredoxin–NADP reductase (EC 1.18.1.2)", "−1.63"], ["P53991", "PETH", "Ferredoxin–NADP reductase, chloroplastic (FNR) (EC 1.18.1.2)", "−1.66"], ["Carbon assimilation", "A8IVM9", "GCSP", "Glycine cleavage system, P protein (EC 1.4.4.2)", "−1.15"], ["Q6SA05", "RCA1", "Rubisco activase", "−1.23"], ["P23489", "RA", "Ribulose bisphosphate carboxylase/oxygenase activase, chloroplastic", "−1.36"], ["Q0ZAZ1", "GDH", "Glycolate dehydrogenase", "−1.37"], ["A8HP84", "GAP3", "Glyceraldehyde‐3‐phosphate dehydrogenase (EC 1.2.1.12) (EC 4.3.2.1)", "−1.47"], ["A8IPI7", "HPR1", "Hydroxypyruvate reductase", "−1.51"], ["A8IRK4", "SEBP1", "Sedoheptulose‐1,7‐bisphosphatase (EC 3.1.3.37)", "−1.53"], ["A8IKW6", "RPE1", "Ribulose‐phosphate 3‐epimerase (EC 5.1.3.1)", "−1.57"], ["A8I5A0", "CPLD45", "Predicted protein", "−1.58"], ["A8IKQ0", "FBP1", "Fructose‐1,6‐bisphosphatase (EC 3.1.3.11)", "−1.65"], ["Q42690", "FBA1", "Fructose‐bisphosphate aldolase 1, chloroplastic (EC 4.1.2.13)", "−1.71"], ["A8IRQ1", "RPI1", "Ribose‐5‐phosphate isomerase (EC 5.3.1.6)", "−1.72"], ["Q75NZ2", "LCIB", "Low‐CO2 inducible protein LCIB", "−1.77"], ["A8JC04", "PGK1", "Phosphoglycerate kinase (EC 2.7.2.3)", "−1.81"], ["P93109", "CA2", "Beta‐carbonic anhydrase", "−1.95"], ["Q39589", "BETA‐CA1", "Carbonic anhydrase", "−2.91"], ["Starch metabolism", "Q2VA40", "PHOA", "Phosphorylase (EC 2.4.1.1)", "1.48"], ["Q2VA41", "PHOB", "Phosphorylase (EC 2.4.1.1)", "1.42"], ["A8HS14", "STA1", "ADP‐glucose pyrophosphorylase (EC 2.7.7.27)", "−1.23"], ["Q9LLL6", "STA6", "ADP‐glucose pyrophosphorylase (EC 2.7.7.27)", "−1.34"], ["O64926", "SS", "Soluble starch synthase (EC 2.4.1.21)", "−1.81"], ["Glycolysis", "A8JHR9", "GAP1A", "Glyceraldehyde 3‐phosphate dehydrogenase, dominant splicing variant (EC 1.2.1.12)", "3.01"], ["A8 IE23", "PGI1", "Glucose‐6‐phosphate isomerase (EC 5.3.1.9)", "−1.22"], ["A8IVR6", "PYK2", "Pyruvate kinase (EC 2.7.1.40)", "−1.70"], ["A8JC04", "PGK1", "Phosphoglycerate kinase (EC 2.7.2.3)", "−1.81"], ["TCA cycle", "A8J2S0", "CIS2", "Citrate synthase (EC 2.3.3.1)", "1.82"], ["A8JHC9", "CIS1", "Citrate synthase", "1.49"], ["A8HMQ1", "ACH1", "Aconitate hydratase (EC 4.2.1.3)", "1.41"], ["Q9FNS5", "MDH5", "NADP‐Malate dehydrogenase (EC 1.1.1.82)", "−1.27"], ["A8HPL8", "DLD2", "Dihydrolipoamide dehydrogenase (EC 1.8.1.4)", "−1.58"], ["A8J7F6", "DLA2", "Dihydrolipoamide acetyltransferase (EC 2.3.1.12)", "−1.59"], ["Mitochondrial electron transfer chain", "A8JDV9", "ATP3", "F1F0 ATP synthase gamma subunit", "−1.17"], ["Q96550", "ATPA", "ATP synthase subunit alpha", "−1.32"], ["Q6V9B1", "NUOS8", "NADH:ubiquinone oxidoreductase subunit 8 (EC 1.6.5.3)", "−1.32"], ["A8IVJ7", "NUOS1", "NADH:ubiquinone oxidoreductase 76 kDa subunit", "−1.49"], ["Q6V9A8", "NUO7", "NADH:ubiquinone oxidoreductase 49 kD subunit (EC 1.6.5.3)", "−1.77"], ["Fatty acid biosynthesis", "A8HPL8", "DLD2*", "Dihydrolipoamide dehydrogenase (EC 1.8.1.4)", "−1.58"], ["A8J7F6", "DLA2*", "Dihydrolipoamide acetyltransferase (EC 2.3.1.12)", "−1.59"], ["A8JFI7", "EAR", "enoyl ACP reductase", "−1.92"], ["A8JGF4", "BC", "Biotin carboxylase, acetyl‐CoA carboxylase component", "−1.98"], ["Tetrapyrrole metabolism", "A8I980", "ALAD", "Delta‐aminolevulinic acid dehydratase (EC 4.2.1.24)", "1.41"], ["A8J7H3", "GSA", "Glutamate‐1‐semialdehyde aminotransferase (EC 5.4.3.8)", "−1.23"], ["A8HNE8", "CHLP", "Geranylgeranyl reductase (EC 1.3.1.‐)", "−1.33"], ["A8HPJ2", "POR", "Light‐dependent protochlorophyllide reductase (EC 1.3.1.33)", "−1.59"], ["Amino acid metabolism", "A8IH03", "PSAT", "Phosphoserine aminotransferase (EC 2.6.1.52)", "3.11"], ["A8J786", "HIS7", "Imidazole glycerol phosphate synthase (Fragment)", "2.95"], ["A8J2X6", "AGGPR", "N‐acetyl‐gamma‐glutamyl‐phosphate reductase", "2.29"], ["A8HXS9", "LEU2", "Isopropylmalate synthase (EC 2.3.3.13) (Fragment)", "2.18"], ["A8IXE0", "SAHH", "S‐Adenosylhomocysteine hydrolase (EC 3.3.1.1)", "1.99"], ["A8JFR4", "OTA1", "Ornithine transaminase (EC 2.6.1.13)", "1.95"], ["A8JG03", "LEU1", "Isopropylmalate dehydratase, large subunit", "1.94"], ["A8J979", "MCCA", "Methylcrotonoyl‐CoA carboxylase alpha subunit", "1.85"], ["A8I826", "HSK1", "Homoserine kinase (EC 2.7.1.39)", "1.81"], ["A8IMY5", "ANS1", "Anthranilate synthase, alpha subunit (Fragment)", "1.70"], ["A8J173", "ASD1", "Aspartate semialdehyde dehydrogenase", "1.62"], ["A8J2Z6", "ChS1", "Chorismate synthase (EC 4.2.3.5)", "1.47"], ["A8IX80", "AAD1", "Acetohydroxyacid dehydratase", "1.46"], ["A8ISB0", "OASTL4", "O‐acetylserine sulphydrolase; cysteine synthase (EC 2.5.1.47)", "1.42"], ["A8J355", "CGS1", "Cystathionine gamma‐synthase", "1.42"], ["A8J3D3", "HIS5", "Histidinol phosphate aminotransferase", "1.41"], ["A8ITU7", "PGD1", "D‐3‐phosphoglycerate dehydrogenase (EC 1.1.1.95)", "1.37"], ["O22547", "ALAS", "Acetolactate synthase", "1.20"], ["A8JIR0", "CPS1", "Carbamoyl phosphate synthase, large subunit (EC 6.3.5.5)", "−1.17"], ["P22675", "ARG7", "Argininosuccinate lyase (ASAL) (EC 4.3.2.1) (Arginosuccinase)", "−1.26"], ["A8I305", "GLN1", "Glutamine synthetase (EC 6.3.1.2)", "−1.43"], ["A8JBL3", "NAGS", "N‐acetylglutamate synthase (Fragment)", "−1.49"], ["Other", "A8IJL3", "MEP‐S", "2‐C‐methyl‐d‐erythritol 2,4‐cyclodiphosphate synthase (EC 4.6.1.12)", "2.02"], ["A8J841", "THICb", "Hydroxymethylpyrimidine phosphate synthase", "2.00"], ["A8HMC0", "CRT2", "Calreticulin 2, calcium‐binding protein", "1.53"], ["Q8LRU1", "FER1", "Pre‐apoferritin", "1.41"], ["Kinases", "A8JDN2", "ADK3", "Adenylate kinase 3 (EC 2.7.4.3)", "−1.97"], ["A8JH12", "–", "Nucleoside diphosphate kinase", "−1.97"], ["Redox proteins", "O22472", "CAT", "Catalase (EC 1.11.1.6)", "2.16"], ["A8HQT1", "PDI2", "Protein disulfide isomerase", "1.54"], ["A8IA77", "GSH1", "Gamma‐glutamylcysteine synthetase (EC 6.3.2.2)", "1.54"], ["A8IVV9", "", "Flavodoxin‐like protein (Fragment)", "−1.16"], ["A8IWK2", "–", "Ferredoxin thioredoxin reductase, catalytic chain", "−2.14"], ["N & S metabolism", "A8JHB4", "GSF1", "Ferredoxin‐dependent glutamate synthase", "1.29"], ["A8IXF1", "ATS1", "ATP‐sulfurylase", "1.15"], ["A8J6A7", "MET16", "Adenylylphosphosulfate reductase", "−1.27"], ["A8JGD1", "GDH2", "Glutamate dehydrogenase", "−1.36"], ["Cell structure/organization", "A8JB85", "APG8", "Autophagy protein", "3.84"], ["A8HW56", "CDC48", "Flagellar associated protein (EC 3.6.1.3)", "2.08"], ["A8J614", "FAP42", "Flagellar associated protein, adenylate/guanylate kinase‐like protein", "1.80"], ["A8IFL6", "FAP262", "Flagellar associated protein", "1.70"], ["A8JEQ8", "FAP79", "Flagellar associated protein", "1.31"], ["A8JAV1", "IDA5", "Actin", "−1.31"], ["P09205", "TUBA2", "Tubulin alpha‐2 chain", "−1.90"], ["A8IXZ0", "TUB1", "Beta tubulin 1 (Beta tubulin 2)", "−2.11"], ["Stress response", "Q39603", "HSP70B", "Heat shock protein 70B", "2.06"], ["A8IZU0", "HSP70C", "Heat shock protein 70C", "1.77"], ["P25840", "HSP70", "Heat shock 70 kDa protein", "1.70"], ["A8I7T1", "HSP90B", "Heat shock protein 90B (Fragment)", "1.62"], ["A8I972", "CLPB3", "ClpB chaperone, Hsp100 family", "1.61"], ["A8HYV3", "HSP70B", "Heat shock protein 70B", "1.32"], ["DNA and RNA metabolism", "A8JFP3", "–", "Histone methyltransferase", "1.34"], ["Q1G2Y1", "PNP", "Chloroplast polyribonucleotide phosphorylase", "1.30"], ["A8IZS5", "–", "Glycine‐rich RNA‐binding protein", "1.23"], ["A8I0F5", "ORC1", "Origin recognition complex subunit 1", "1.21"], ["A8JCT1", "HBV1", "Histone H2B", "−1.77"], ["A8HWY2", "HTR14", "Histone H3 (Fragment)", "−1.88"], ["A8HVA3", "HFO4", "Histone H4", "−1.91"], ["A8JIN9", "HFO43", "Histone H4", "−1.92"], ["A8HRZ9", "H2A", "Histone H2A", "−1.95"], ["Transporters", "A8JGB0", "–", "Arsenite translocating ATPase‐like protein (Fragment)", "1.44"], ["A8I164", "ATPVA1", "Vacuolar ATP synthase, subunit A", "−1.18"], ["A8I268", "HLA3", "ABC transporter", "−2.40"]], "row_count": 155, "column_count": 5, "numeric_cells": 331, "header_rows": 1, "locator": "section[12]/table-wrap[1]#nph14832-tbl-0001"}}], "gaps": ["asset:data:geo:PXD005046 not downloaded", "asset:data:geo:PXD005046 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To avoid using arbitrary thresholds for highlighting differentially expressed proteins, a t‐test was performed between replicate conditions to determine significance with fold change."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (t-test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["PXD005046"], "resolved_accessions": ["PXD005046"], "statements": ["Data are available via ProteomeXchange (PXD005046)."], "basis": "The paper names PXD005046 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29034959", "data:geo:PXD005046", "asset:table:pmid:29034959:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005046"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:10:20Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 48361, "completion_tokens": 1002, "cached_tokens": 15880}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:29034959", "type": "paper", "label": "pmid:29034959"}, {"id": "source:pmid:29034959", "type": "manuscript", "label": "PMID 29034959 full text"}, {"id": "data:geo:PXD005046", "type": "dataset", "label": "GEO PXD005046"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29034959", "type": "paper", "label": "pmid:29034959"}, {"id": "source:pmid:29034959", "type": "manuscript", "label": "PMID 29034959 full text"}, {"id": "data:geo:PXD005046", "type": "dataset", "label": "GEO PXD005046"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29034959", "type": "extraction", "used": ["source:pmid:29034959"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005046", "type": "accession_resolution", "used": ["data:geo:PXD005046"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:29034959", "parent_hash": "sha256:787802de890abbed9abf5e9fb7dc921a0c231faef136a507a0cf6f693a5d3a57", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD005046 licence not read", "asset:data:geo:PXD005046 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["e‐quantitative polymerase chain reaction (RT‐qPCR) Table S2 Optimized values for MS analysis o"], "order_basis": "paper_text_order:3908", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:16:45+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}